How can Big Data from Social Media be used in Emergency Management? A case study of Twitter during the Paris attacks

Abstract

Over the past years, social media have impacted emergency management and disaster response in numerous ways. The access to live, continuous updates from the public brings new opportunities when it comes to detecing, coordinating and aiding in an emergency situation. The thesis present a research of social media during an emergency situation. The goal of the study is to discover how data from social media can be used for emergency management and determine if existing analysis services can be proven useful for the same occasion. To achieve the goal, a dataset from Twitter during the Paris attacks 2015 was collected. The dataset was analyzed using three different analysis tools; IBM Watson Discovery service, Microsoft Azure Text Analytics and an own developed Keyword Frequency Script. The results indicate that data from social media can be used for emergency management, in form of detecting and providing important information. Additional testing with larger datasets is needed to fully demonstrate the usefulness, in addition to interviews with emergency responders and social media users.